Ollama API Pricing: Pay Per Token
This is a prepaid, pay-per-token API for uncensored inference. You load crypto credit, send requests, and pay only for the tokens actually used.
- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Cost estimator
Usage examples
Long context reasoning with short answers
Input: 50,000 tokens ($0.15/1M = $0.0075). Output: 1,000 tokens ($0.50/1M = $0.0005). Total: $0.008.
Streaming chat with moderate length
Input: 10,000 tokens ($0.0015). Output: 5,000 tokens ($0.0025). Total: $0.004.
Large batch processing
Input: 200,000 tokens ($0.03). Output: 20,000 tokens ($0.01). Total: $0.04.
Prepaid Crypto Balance and Bonus Credits
Your API key draws from a prepaid balance. You top up using USDT (TRC20) or USDC (Base) for amounts between $20 and $500. The system credits your account with bonus value: 5% extra on $50+, 10% on $100+, and 15% on $200+. This bonus never expires.
Errors consume zero tokens, so failed requests do not reduce your balance. You only pay for successful token generation.
Rate Limits and Concurrency
Each API key supports 300 requests per minute and 8 concurrent connections. Request bodies must stay under 8 MB. These limits ensure stable throughput for your uncensored LLM API workflows.
One key per account. Replace the old key with a new one if needed. The system tracks usage in real time.
Trial Credit and Refund Policy
New accounts get $0.50 trial credit valid for 7 days. Sign up with Google or email. Credits never expire. Mistakes like double charges are fixed via Support. Credits are non-refundable.
Common questions
Does the API documentation support embeddings or image generation?
No. The API only handles text chat completions. It does not support embeddings, images, audio, or video. You send text and get text back. Use this model for conversational or reasoning tasks.
How do I top up my crypto balance?
Send USDT (TRC20) or USDC (Base) from $20 to $500. You receive bonus credit based on your top-up amount. The credit is added to your prepaid balance immediately.
What happens if a request fails?
Failed requests consume zero tokens. You only pay for tokens successfully generated. Errors do not reduce your prepaid balance. This keeps your costs predictable.
Can I use this uncensored LLM API for commercial projects?
Yes. Use it for lawful adult content, research, or development. The model does not refuse controversial topics. Minors in sexual content remain restricted.
Get your key in seconds
Sign up, grab the key, swap the base URL. Done.
